Claim Verification on Mocheg
49.7Macro F1MEVER
Evaluation Results
| Method | Links | |
|---|---|---|
| MEVEREvidence Setting=Retrieved2026.02 | 49.7 | |
| GPT-4oEvidence Setting=Gold2026.02 | 48.7 | |
| MEVEREvidence Setting=Gold2026.02 | 48.3 | |
| CCNEvidence Setting=Retrieved2026.02 | 47.5 | |
| KGATEvidence Setting=Gold2026.02 | 47.4 | |
| ESCNetEvidence Setting=Retrieved2026.02 | 47.4 | |
| ECENetEvidence Setting=Retrieved2026.02 | 46.7 | |
| ESCNetEvidence Setting=Gold2026.02 | 46.4 | |
| MultiKE-GATEvidence Setting=Retrieved2026.02 | 46.2 | |
| MEVER w/o imagesEvidence Setting=Retrieved2026.02 | 46.2 | |
| CORRECTEvidence Setting=Gold2026.02 | 46 | |
| CORRECTEvidence Setting=Retrieved2026.02 | 45.9 | |
| RAVEvidence Setting=Gold2026.02 | 45.8 | |
| MochegModelEvidence Setting=Gold2026.02 | 45.6 | |
| MochegModelEvidence Setting=Retrieved2026.02 | 45.5 | |
| ECENetEvidence Setting=Gold2026.02 | 45.5 | |
| MEVER w/o imagesEvidence Setting=Gold2026.02 | 45.4 | |
| KGATEvidence Setting=Retrieved2026.02 | 45.1 | |
| TransformerXH++Evidence Setting=Gold2026.02 | 45 | |
| CCNEvidence Setting=Gold2026.02 | 44.9 | |
| TransformerXH++Evidence Setting=Retrieved2026.02 | 44.5 | |
| MR2RetrievedEvidence Setting=Retrieved2026.02 | 44.5 | |
| GPT-4oEvidence Setting=Retrieved2026.02 | 44.5 | |
| JustiLMEvidence Setting=Retrieved2026.02 | 44.4 | |
| TransformerXHEvidence Setting=Retrieved2026.02 | 44.3 | |
| MR2RetrievedEvidence Setting=Gold2026.02 | 44 | |
| TransformerXHEvidence Setting=Gold2026.02 | 43.8 | |
| RAVEvidence Setting=Retrieved2026.02 | 42.5 | |
| MultiKE-GATEvidence Setting=Gold2026.02 | 39.9 | |
| CausalWalkEvidence Setting=Gold2026.02 | 38.6 | |
| JustiLMEvidence Setting=Gold2026.02 | 38.5 | |
| CausalWalkEvidence Setting=Retrieved2026.02 | 30.1 |